krzysiek
Joined 10 years ago
Joined 10 years ago
One thing I find especially intriguing is how LLMs can help deal with desinformation:
- I experiment with deterministic settings of local LLMs for the document summary so that sharing a prompt would prove that the output was not tempered with (no desinformation on the service side)
- I add outputs of several LLMs (from the US, the EU and from China) for the "broader context" section so users could compare the output (no desiformation on the provider and model side)
You could try coaching (look for ICF certified, or if you're in UK, AC certified coach). This would help you find goals that trully matter TO YOU, and develop fulfilling process for reaching these goals.
You could also try pschoterapy. This could help you be more self-aware and develop mental skills for dealing with feelings that you described.
I mean it's like saying that having a choice before being educated by one of the parties among the choices is a bad thing and it looks bad.
It seems to me that building expectations based on social media (e.g. just by browsing) is the real problem, not posting or not.
The core idea is identifying features where you answer "yes" to the question: "Could you demo it?"
Regarding the value of such tools when working with codebases whith heavy coding agent use - absolutely. Especially when code generated by models such as Astra can be pretty unreadable (https://news.ycombinator.com/item?id=49654229)